Using Hyperbolic Tangent Function for Nonlinear Profile Monitoring

For most of the Statistical process control (SPC) applications, the quality of a process or product is measured by one or multiple quality characteristics. In some particular circumstances, quality characteristics depend on the relationship between the response variable and one and/or explanatory variables. Therefore, such a quality characteristic is represented by a function or a curve, which is called a ‘profile’. In this paper, a new method of using the hyperbolic tangent function will be addressed for modeling the vacuum heat treatment process data. The hyperbolic tangent function approach is compared to the smoothing spline approach when modeling the nonlinear profiles. The vector of parameter estimates is monitored by using the Hotelling’s T 2 for the parametric approach and by the metrics method for the nonparametric approach. In Phase I, the proposed hyperbolic tangent approach is able to correctly identify the outlying profiles.